© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51369
    Prev
    Next
    INDEX
    Explanations

    numbers after math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Å¡e
    -0.08
    heet
    -0.07
     <--
    -0.07
    ezen
    -0.07
     rele
    -0.06
    иб
    -0.06
    被åijĬçŁ¥
    -0.06
    ...)
    -0.06
     real
    -0.06
    èĽĭ
    -0.06
    POSITIVE LOGITS
    èģĺ
    0.07
    -mf
    0.07
    loom
    0.07
    antas
    0.07
    eshire
    0.07
    åįıè®®çļĦ
    0.07
    æijĩæijĩ
    0.07
    antau
    0.07
    imente
    0.07
    ieso
    0.07
    Activations Density 0.008%

    No Known Activations